FLICKER: A Fine-Grained Contribution-Aware Accelerator for Real-Time 3D Gaussian Splatting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910036987478016 |
|---|---|
| author | Ou, Wenhui Wu, Zhuoyu Zhang, Yipu Wu, Dongjun Hong, Freddy Ziyang Yue, Chik Patrick |
| author_facet | Ou, Wenhui Wu, Zhuoyu Zhang, Yipu Wu, Dongjun Hong, Freddy Ziyang Yue, Chik Patrick |
| contents | Recently, 3D Gaussian Splatting (3DGS) has emerged as a mainstream rendering technique due to its photorealistic quality and low latency. However, processing massive numbers of non-contributing Gaussian points introduces significant computational overhead on resource-limited edge platforms, limiting its deployment in next-generation AR/VR devices. Contribution-based prior skipping alleviates this inefficiency, yet the resulting contribution-testing workload becomes prohibitive for edge execution. In this paper, we present FLICKER, a contribution-aware 3DGS accelerator based on hardware-software co-design. The proposed framework integrates adaptive leader pixels, pixel-rectangle grouping, hierarchical Gaussian testing, and a mixed-precision architecture to enable near pixel-level, contribution-driven rendering with minimal overhead. Experimental results demonstrate up to $1.5\times$ speedup, $2.6\times$ improvement in energy efficiency, and $14%$ area reduction compared with a state-of-the-art accelerator. Compared with a representative edge GPU, FLICKER achieves a $19.8\times$ speedup and $26.7\times$ higher energy efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01158 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FLICKER: A Fine-Grained Contribution-Aware Accelerator for Real-Time 3D Gaussian Splatting Ou, Wenhui Wu, Zhuoyu Zhang, Yipu Wu, Dongjun Hong, Freddy Ziyang Yue, Chik Patrick Hardware Architecture Recently, 3D Gaussian Splatting (3DGS) has emerged as a mainstream rendering technique due to its photorealistic quality and low latency. However, processing massive numbers of non-contributing Gaussian points introduces significant computational overhead on resource-limited edge platforms, limiting its deployment in next-generation AR/VR devices. Contribution-based prior skipping alleviates this inefficiency, yet the resulting contribution-testing workload becomes prohibitive for edge execution. In this paper, we present FLICKER, a contribution-aware 3DGS accelerator based on hardware-software co-design. The proposed framework integrates adaptive leader pixels, pixel-rectangle grouping, hierarchical Gaussian testing, and a mixed-precision architecture to enable near pixel-level, contribution-driven rendering with minimal overhead. Experimental results demonstrate up to $1.5\times$ speedup, $2.6\times$ improvement in energy efficiency, and $14%$ area reduction compared with a state-of-the-art accelerator. Compared with a representative edge GPU, FLICKER achieves a $19.8\times$ speedup and $26.7\times$ higher energy efficiency. |
| title | FLICKER: A Fine-Grained Contribution-Aware Accelerator for Real-Time 3D Gaussian Splatting |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2603.01158 |